INDEX

Explanations

terms related to data processing and analysis, particularly in a technical or scientific context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/read

-0.22

/right

-0.21

 rigorous

-0.19

-Russian

-0.19

Body

-0.18

 readily

-0.18

 reasoned

-0.18

 rural

-0.17

 routine

-0.17

 reasoning

-0.17

POSITIVE LOGITS

efined

0.21

mond

0.19

-ÑĤÐ°ÐºÐ¸

0.19

cliffe

0.18

orative

0.18

forcement

0.18

asmus

0.17

aldo

0.17

ourke

0.17

ansom

0.16

Activations Density 3.156%

terms related to data processing and analysis, particularly in a technical or scientific context

No Comments

No Known Activations